发明名称 |
Determining images of article for extraction |
摘要 |
A content application determines images of an article for extraction. The content application identifies an initial image associated with a content of the article. A caption and a credit line associated with the initial image is detected and the initial image is extracted along with the caption and the credit line. A second image of the article associated with a video is also detected and extracted along with the video. In addition, the content application extracts a slideshow detected within the article. |
申请公布号 |
US9117280(B2) |
申请公布日期 |
2015.08.25 |
申请号 |
US201314037177 |
申请日期 |
2013.09.25 |
申请人 |
Microsoft Technology Licensing, LLC |
发明人 |
Chen Yu;Song Ruihua;Gao Guangping;Zhang Qian;Liu Ming;Narayanan Raman;Gu Shelley Summer;Gouw Yanti Aruswati |
分类号 |
G06K9/34;G06T7/00;G06K9/00 |
主分类号 |
G06K9/34 |
代理机构 |
|
代理人 |
Meyers Jessica;Ross Jim;Mihas Micky |
主权项 |
1. A method executed on a computing device for determining images of an article for an extraction, the method comprising:
identifying a first image associated with a content of the article; detecting a caption and a credit line associated with the first image; extracting the first image, the caption, and the credit line; detecting a second image of the article associated with an embedded video; extracting the second image and the video; detecting a slideshow within the article; and extracting the slideshow. |
地址 |
Redmond WA US |